Agent skill · software engineering · jeremylongshore
j-rig
Skill Refiner, the eval-guided improvement loop for SKILL.md files. Runs the bootstrap, score, propose, apply, and status cycle as a thin wrapper over the published @intentsolutions/refiner CLI, proposing safe, minimal, bounded SKILL.md edits and accepting an edit only when a held-out eval score strictly improves with no regression on any other case. Ships a 3-layer cost-tiered hook architecture (sinker, line, hook) that gates skill quality at edit time, end of turn, and commit time. Use when improving an existing skill, refining a SKILL.md against measured behavior, bootstrapping an eval set for a skill, or gating skill edits before they ship. Trigger with "/j-rig", "refine this skill", "bootstrap an eval set", "propose a skill edit", "promote the candidate", or "skill refiner status".
Why this skill is useful
Adds a CLI tool that automates the skill refinement process with bounded edits and eval scoring, enhancing the AI's ability to improve existing skills.
What it needs
Requires @intentsolutions/jrig-cli installed locally. Requires anthropic account access. About 6k tokens when loaded. Last updated 2026-08-07. 2,604 stars on the source repository.
What this skill does
j-rig — Skill Refiner Overview The Skill Refiner is the eval-guided improvement loop for SKILL.md files. It analyzes an existing skill against measured behavior, proposes safe, minimal, bounded edits, and accepts an edit only when it strictly improves. It is the second product in the Intent Solutions agent-rig stack: The refiner proposes bounded edits (add, delete, or replace operations on the SKILL.md text) and accepts an edit only if a held-out eval score strictly improves with no regression on any other case. It never rewrites a skill wholesale, and it never lets a skill judge itself; scoring is delegated to the separate j-rig eval harness. This plugin is a thin wrapper. The refiner logic lives in the published @intentsolutions/refiner package and is exposed through the j-rig refine command group in the @intentsolutions/jrig-cli binary. This skill invokes that CLI; it does not reimplement any refiner logic. Use this skill when: Improving an existing skill whose behavior you can measure. Bootstrapping a held-out eval set for a skill so you have something to score against. Proposing a bounded SKILL.md edit and checking whether it strictly improves. Gating skill edits before they ship (the 3-layer hooks do this automatically). Do NOT use it to hand-author a brand-new skill from scratch; use /skill-creator for that. The refiner improves skills that already exist and already have measurable behavior. Prerequisites The subcommands wrap the published j-rig binary. Install it once: The refine command group is contributed by @intentsolutions/refiner, which ships as a dependency of the CLI. Model-backed steps (score, propose) require the ANTHROPICAPIKEY environment variable; the deterministic steps (bootstrap, apply, status) run fully offline. Instructions Each /j-rig subcommand maps one-to-one onto a j-rig refine verb. Run them against a skill directory (the folder containing the SKILL.md). …
How to use it
Reference it in AdaL, Claude Code, Cursor or any coding agent — nothing to install:
@skills jeremylongshore/j-rig--764215